| Summary: | 碩士 === 中華大學 === 工業管理學系 === 104 === With technological products flourish with each passing day, consumers on the visual senses and more demanding than ever before, stimulating demand for flat panel display industry is obvious, in 2015 the global flat panel display industry into a deep restructuring and the rapid development of all, the pace of upgrades continues to accelerate, monitor important elements of a color filter is bound to increasingly thin, but also to make flat panel displays colored uniform rendered. However, there is a color filter production must first make its color photo resist, when the color resist lithography process parameter settings, often need to rely on the experience of researchers, by a factor of one way to find the combination of process parameters, ignore the interaction between factors, so that research results.
From the outset of discussing with engineers in terms of past related literature survey of a photolithography process, the quality characteristics of product and control variables can be well-ascertained, then transforming the problem from multi-objective quality characteristics combing into a single quality characteristic using the experimental planning of Taguchi method and analysis of variables(ANOVA). Moreover, identifying the relationships between control factors of experiments and signal-to-noise (S/N) ratios and quality characteristics through the data analyses comprising main effects and interactions of factors and analysis of variables (ANOVA). As a result, the crucial control factors can be found by main effects and interactions graphs of factors in terms of signal-to-noise (S/N) ratios, and the better Taguchi parameter settings can also be obtained through the sorting of control factors in the multi-quality characteristics situation. However, the optimal parameter settings (Solution) through the Taguchi experimental planning is still belong to a discrete optimal solution, and unnecessarily meet the process stability and quality goals. Therefore, the study firstly identifies the initial weight of back-propagation neural networks (BPNN) using hybrid PSO-GA with multilayer perceptron (MLP), secondly improves the BPNN training efficiency and precision by regarding the optimal weight as BPNN initial value, and then implementing to train and test the BPNN; finally, the study constructs the signal-to-noise (S/N) ratios and quality characteristics predictors combining with hybrid PSO-GA, and analysis of variable (ANOVA) to locate the significant control factors, serves the parameter settings of Taguchi experimental design as the initial value, proceeds to analyze the data, and further pinpoint the optimal parameter settings which can achieve the quality goal and reach the process stability at the same time.
|
|---|
